Vehicle data storage method and device, electronic equipment and readable storage medium

Abstract

The invention discloses a vehicle data storage method and device, electronic equipment and a readable storage medium, and the method comprises the steps: collecting the data of an automatic driving domain and the data of a cabin domain, and adding the data of the automatic driving domain and the data of the cabin domain to an original data set; obtaining a first data set in the original data set, and performing data enhancement operation on first data in the first data set to obtain enhanced data corresponding to the first data; adding the enhanced data and the original data in the original data set to a merged data set, and preprocessing the data in the merged data set to obtain preprocessed data of the data in the merged data set; and performing distributed storage on the preprocessed data according to the characteristics of the preprocessed data. According to the method and the device, the types of the obtained data are more, the complexity of user query can be reduced, and the user experience is improved.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular relates to a vehicle data storage method, device, electronic device and readable storage medium. Background Art

[0002] Vehicle information is provided through wireless communication, satellite navigation and other technologies, allowing users to obtain information on the vehicle's operating status during driving.

[0003] Related technologies usually use on-board sensors to obtain vehicle-related data in the autonomous driving domain, for example, obtaining vehicle external environment data through cameras, obtaining the vehicle's position through radars, and obtaining the distance between the vehicle and obstacles through ultrasonic sensors, and storing the obtained data in the autonomous driving domain.

[0004] However, the related technology obtains information in the autonomous driving domain, the types of data obtained are relatively small, and the obtained data is stored in the autonomous driving domain. When users query data, the query method is relatively complicated and the user experience is poor. Summary of the invention

[0005] The present invention aims to provide a vehicle data storage method, device, electronic device and readable storage medium, which at least solves the problem that in the prior art, information in the autonomous driving domain is obtained, the types of data obtained are relatively small, and the obtained data is stored in the autonomous driving domain. When the user queries the data, the query method is relatively complicated and the user experience is poor.

[0006] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0007] In a first aspect, an embodiment of the present invention provides a vehicle data storage method, comprising:

[0008] Collecting data from an autonomous driving domain and data from a cockpit domain, and adding the data collected from the autonomous driving domain and the cockpit domain to an original data set; the autonomous driving domain is a domain related to assisted driving; the cockpit domain is a domain related to internal vehicle interaction;

[0009] Acquire a first data set in the original data set, perform a data enhancement operation on first data in the first data set, and obtain enhanced data corresponding to the first data; the first data set includes data obtained in a preset state;

[0010] Adding the enhanced data and the original data in the original data set to a merged data set, performing a preprocessing operation on the data in the merged data set, and obtaining preprocessed data of the data in the merged data set;

[0011] The preprocessed data is distributedly stored according to the characteristics of the preprocessed data.

[0012] In a second aspect, an embodiment of the present invention further provides a vehicle data storage device, comprising:

[0013] a collection module, used to collect data from an autonomous driving domain and data from a cockpit domain, and add the data collected from the autonomous driving domain and the cockpit domain to an original data set; the autonomous driving domain is a domain related to assisted driving; the cockpit domain is a domain related to internal vehicle interaction;

[0014] A data enhancement module, used to obtain a first data set in the original data set, perform a data enhancement operation on the first data in the first data set, and obtain enhanced data corresponding to the first data; the first data set includes data obtained in a preset state;

[0015] A preprocessing module, used for adding the enhanced data and the original data in the original data set to the merged data set, performing a preprocessing operation on the data in the merged data set, and obtaining the preprocessed data of the data in the merged data set;

[0016] The storage module is used to perform distributed storage on the preprocessed data according to the characteristics of the preprocessed data.

[0017] In a third aspect, an embodiment of the present invention further provides an electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the vehicle data storage method as described in the first aspect.

[0018] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the vehicle data storage method as described in the first aspect are implemented.

[0019] In summary, the embodiment of the present invention collects data in the autonomous driving domain and data in the cockpit domain, adds the data in the autonomous driving domain and data in the cockpit domain to the original data set, obtains the first data set in the original data set, performs data enhancement operation on the first data in the first data set, obtains enhanced data corresponding to the first data, adds the enhanced data and the original data in the original data set to the merged data set, performs preprocessing operation on the data in the merged data set, and obtains preprocessed data of the data in the merged data set. In addition, the data in the autonomous driving domain and the cockpit domain are collected, and the first data in the autonomous driving domain and the cockpit domain are enhanced. The types of data obtained are more and more comprehensive. In addition, according to the characteristics of the preprocessed data, the preprocessed data is distributedly stored, and the preprocessed data is stored in an appropriate location. The data can be obtained according to the storage location of the preprocessed data, rather than from the domain to which the data belongs. Therefore, when the user queries the data, the complexity of the user query can be reduced, and the user experience is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flowchart of a vehicle data storage method provided by an embodiment of the present invention;

[0021] Figure 2 is a flowchart of another vehicle data storage method provided by an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of a microphone array provided by an embodiment of the present invention;

[0023] Figure 4 is a schematic diagram of an original image provided by an embodiment of the present invention;

[0024] Figure 5 is a schematic diagram of an enhanced image provided by an embodiment of the present invention;

[0025] Figure 6 is a schematic diagram of a data storage system provided by an embodiment of the present invention;

[0026] Figure 7 is a schematic diagram of speech-to-text conversion provided by an embodiment of the present invention;

[0027] Figure 8 is a flow chart of an encryption method provided by an embodiment of the present invention;

[0028] Fig. 9 is a flow chart of another encryption method provided by an embodiment of the present invention;

[0029] Fig.10 is a schematic diagram of another data storage system provided by an embodiment of the present invention;

[0030] Fig.11 is a user interaction schematic diagram provided by an embodiment of the present invention;

[0031] Fig.12 is a block diagram of a vehicle data storage device provided by an embodiment of the present invention;

[0032] Fig.13 is a block diagram of an electronic device provided by an embodiment of the present invention;

[0033] Fig.14 is a block diagram of another electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The memory training method provided by the embodiment of the present invention is described in detail below through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0035] In the modern intelligent driving environment, the demand for personalized information is growing. As the types of car driving and related data become more diverse and complex, how to effectively collect, store, and pre-process this data, while laying a solid foundation for future large-scale model training, has become a key issue in realizing personalized services.

[0036] Related technologies usually use on-board sensors to obtain vehicle-related data in the autonomous driving domain, for example, obtaining vehicle external environment data through cameras, obtaining vehicle position through radars, and obtaining the distance between vehicles and obstacles through ultrasonic sensors, and storing the obtained data in the autonomous driving domain. However, related technologies obtain information in the autonomous driving domain, the types of data obtained are relatively small, and the obtained data is stored in the autonomous driving domain, so when users query data, the query efficiency is low.

[0037] In an embodiment of the present invention, by collecting data in the autonomous driving domain and data in the cockpit domain, and adding the data in the autonomous driving domain and data in the cockpit domain to the original data set, obtaining a first data set in the original data set, performing a data enhancement operation on the first data in the first data set, obtaining enhanced data corresponding to the first data, adding the enhanced data and the original data in the original data set to the merged data set, performing a preprocessing operation on the data in the merged data set, and obtaining preprocessed data of the data in the merged data set, not only the data in the autonomous driving domain but also the data in the cockpit domain are collected, and the enhancement operation is performed on the first data in the autonomous driving domain and the cockpit domain, so that the types of data obtained are more and more comprehensive. In addition, according to the characteristics of the preprocessed data, the preprocessed data is distributedly stored, and the preprocessed data is stored in an appropriate location. The data can be obtained according to the storage location of the preprocessed data, rather than from the domain to which the data belongs. Therefore, when a user queries data, the complexity of the user query can be reduced, and the user experience is improved.

[0038] Figure 1 A vehicle data storage method provided by an embodiment of the present invention is referred to Figure 1 , the method comprises the following steps:

[0039] Step 101, collect data from the autonomous driving domain and the cockpit domain, and add the data from the autonomous driving domain and the cockpit domain to the original data set; the autonomous driving domain is a domain related to assisted driving; the cockpit domain is a domain related to internal vehicle interaction.

[0040] For example, the autonomous driving domain is mainly responsible for sensing the surrounding environment, making decisions, and controlling the vehicle. It requires multiple external sensors, such as cameras, millimeter-wave radars, and lidars, to formulate corresponding strategies and perform lateral and longitudinal control of the vehicle through data processing and multi-sensor information fusion.

[0041] For example, the cockpit domain needs to support some applications, such as voice recognition, gesture recognition, etc., provide excellent display performance support, support virtualization technology, support one-chip multi-screen display, and meet the display needs of instrument screens and central control screens of various sizes.

[0042] For example, the vehicle's built-in sensors, such as the global positioning system (GPS), camera, radar, and external data interface, are used to collect data in the autonomous driving domain and the cockpit domain in real time. The data in the autonomous driving domain reflects the vehicle status and the driving environment of the vehicle, and the data in the cockpit domain reflects the user's behavior.

[0043] For example, after collecting data in the autonomous driving domain and the cockpit domain, data visualization tools can be used to analyze and visualize the data, such as Power BI and Qlik. Data processing tools can also be used to process the data, such as Apache Spark, or industry-specific analysis software can be used, such as SAS and SPSS.

[0044] For example, the present invention can effectively integrate multiple data sources inside and outside the vehicle, build a comprehensive data ecosystem to support intelligent driving assistance and vehicle management functions. Through data enhancement and preprocessing technology, it provides a solid foundation for subsequent personalized services and data analysis, and also lays the foundation for future large model training and data cloud processing solutions.

[0045] Step 102, obtaining a first data set in the original data set, performing a data enhancement operation on first data in the first data set, and obtaining enhanced data corresponding to the first data; the first data set includes data obtained under a preset state.

[0046] For example, data augmentation operations can generate new data instances from existing data using complex algorithmic models. This capability enables vehicles to simulate and predict future situations, providing more information support for decision-making.

[0047] For example, the data obtained in the preset state is usually difficult to obtain and the amount is small. For example, the first data can be the driver's facial expression of fear, or a screaming voice, or the steering wheel rotation and emergency braking reaction time.

[0048] For example, although driving-related data in multiple dimensions and scenarios have been collected, it is still difficult to obtain rare and special data such as extreme driving behavior data, data under severe weather conditions, and privacy-sensitive data. Therefore, considering the use of data enhancement methods, the training data set can be effectively expanded, which is crucial to improving the safety and reliability of both the field of autonomous driving and subsequent related vertical domain applications.

[0049] Step 103: Add the enhanced data and the original data in the original data set to the merged data set, perform a preprocessing operation on the data in the merged data set, and obtain preprocessed data of the data in the merged data set.

[0050] For example, preprocessing operations are to clean, preliminarily analyze and classify the data in the merged data set for more complex processing and analysis, which can significantly improve the efficiency and accuracy of subsequent data processing. Since multi-dimensional data is collected and the types of data are various, it is a better solution to adopt different analysis and processing strategies for different types of data.

[0051] For example, after obtaining the preprocessed data, deep learning technology can be applied to extract useful information from a large amount of complex data to support personalized settings and intelligent decision-making, and enhance driving safety and comfort. It can also automatically adjust the in-car environment based on the driver's historical data and preferences. For example, temperature, seat adjustment, music playback, and provide route optimization suggestions to truly achieve a personalized driving experience. It can also continuously monitor vehicle performance, predict and warn of potential maintenance problems in advance, reduce failure rates and increase vehicle service life. It can also perform automated feedback and continuous optimization, continuously collect user feedback and performance data, and continuously improve system performance and user experience through self-learning and algorithm optimization.

[0052] For example, the present invention provides a comprehensive and efficient data management architecture for an intelligent driving system through personalized information collection, data enhancement and preprocessing of multiple driving data.

[0053] Step 104: Distributed storage of the preprocessed data according to the characteristics of the preprocessed data.

[0054] For example, for multiple types of data, simple database storage can no longer meet the requirements of massive data and real-time fast processing. Therefore, for different types of data, different data storage technologies should be reasonably selected to ensure the reliability, high performance and cost-effectiveness of various types of vehicle-mounted data, providing a good data foundation for subsequent data analysis, processing and application.

[0055] For example, a distributed storage system is used to store large-scale, unstructured data. The distributed storage system can utilize the parallel processing capabilities of multiple nodes to improve the throughput and response speed of data reading and writing. It can also dynamically adjust storage capacity and computing resources according to demand. Data can be backed up on multiple nodes to improve data reliability and fault tolerance.

[0056] For example, preprocessed data can be applied to a variety of data-intensive industries. For example, healthcare: using similar architectures to collect and analyze patient data, support remote monitoring, disease prediction, and health management; configure more adaptable machine learning models for disease diagnosis and medical image analysis; smart cities: applied to traffic flow monitoring, environmental monitoring, and urban safety. Combine IoT technology for real-time data collection and analysis of urban facilities; financial services: used for real-time monitoring and analysis of transaction data, risk management, and fraud detection; integrate artificial intelligence models for customer service automation and personalized financial product recommendations; retail and e-commerce: analyze consumer purchasing behavior, optimize inventory management, and product recommendation systems. Use artificial intelligence to analyze consumer sentiment and improve customer service experience.

[0057] In an embodiment of the present invention, by collecting data in the autonomous driving domain and data in the cockpit domain, and adding the data in the autonomous driving domain and data in the cockpit domain to the original data set, obtaining a first data set in the original data set, performing a data enhancement operation on the first data in the first data set, obtaining enhanced data corresponding to the first data, adding the enhanced data and the original data in the original data set to the merged data set, performing a preprocessing operation on the data in the merged data set, and obtaining preprocessed data of the data in the merged data set, not only the data in the autonomous driving domain but also the data in the cockpit domain are collected, and the enhancement operation is performed on the first data in the autonomous driving domain and the cockpit domain, so that the types of data obtained are more and more comprehensive. In addition, according to the characteristics of the preprocessed data, the preprocessed data is distributedly stored, and the preprocessed data is stored in an appropriate location. The data can be obtained according to the storage location of the preprocessed data, rather than from the domain to which the data belongs. Therefore, when a user queries data, the complexity of the user query can be reduced, and the user experience is improved.

[0058] Figure 2 is a flowchart of another vehicle data storage method provided by an embodiment of the present invention, referring to Figure 2 , the method may include the following steps:

[0059] Step 201, collect data from the autonomous driving domain and the cockpit domain, and add the data from the autonomous driving domain and the cockpit domain to the original data set; the autonomous driving domain is a domain related to assisted driving; the cockpit domain is a domain related to internal vehicle interaction.

[0060] This step may specifically refer to the above step 101, which will not be described in detail here.

[0061] The data in the autonomous driving domain includes: vehicle data; the data in the cockpit domain includes: driver data and voice data;

[0062] The driver data includes: driver's physiological data, driver's facial data, and driver's driving operation data;

[0063] The voice data includes: voice data between the driver and the vehicle system, and voice data between the driver and the passenger;

[0064] The vehicle data includes: the working status of vehicle components, the vehicle's driving speed, the vehicle's geographic coordinates, the vehicle's driving trajectory, the vehicle's temperature, the vehicle's air quality, and the distance between the vehicle and surrounding obstacles.

[0065] For example, the driver's physiological data may include: the driver's heart rate, body temperature, and activity level. The driver's facial data may include: the driver's facial expression and sight direction. The driver's driving operation data may include: the driver's grip strength and steering angle of the steering wheel.

[0066] For example, by collecting the driver's physiological data, facial data, and operation data, it can provide rich data support for subsequent driving behavior analysis, safety warning and other applications.

[0067] For example, for driver data, a complete driver data collection system can be built using devices such as smart watches, in-car cameras, and steering wheel sensors. Smart watches can collect the driver's heart rate, body temperature, activity level and other physiological data in real time; in-car cameras monitor the driver's facial expressions and line of sight; steering wheel sensors can monitor the driver's grip strength, steering angle and other driving operation data.

[0068] For example, by collecting voice data in the cockpit, such as the voice data between the driver and the vehicle system, and the voice data between the driver and the passenger, basic data support can be provided for further understanding the semantics of the driver or passenger and providing more humane services.

[0069] For example, for voice data, a high-quality microphone array can be used to capture the voice data of the driver and the vehicle system, and the voice data of the driver and the passengers in real time. Figure 3 , by using 6 microphones 31 to collect voice data.

[0070] For example, by collecting the working status of vehicle components, the vehicle's driving speed, the vehicle's geographic coordinates, and the vehicle's driving trajectory, it can comprehensively and accurately provide rich data support for applications such as vehicle status monitoring, fault diagnosis, and intelligent driving. By collecting the vehicle's temperature, the vehicle's air quality, and the distance between the vehicle and surrounding obstacles, it can comprehensively and dynamically collect various data about the vehicle's surrounding environment, providing rich data support for applications such as driving decision support and active safety.

[0071] For example, for vehicle data, a complete vehicle data collection system can be built using dedicated sensors of the engine power control unit (ECU), millimeter wave sensors, and on-board equipment such as radar and ultrasonic sensors. The ECU dedicated sensors can directly monitor the working status of key engine components, and the millimeter wave sensors can directly detect the vehicle's driving speed to ensure the accuracy of the detection. An integrated high-precision GPS module can be used to obtain the vehicle's geographic coordinates, driving trajectory and other information in real time. On-board temperature and humidity sensors are used to monitor the climate and environmental data inside and outside the vehicle in real time, which is more real-time and accurate than directly obtaining temperature data through the Internet. Ultrasonic sensors and lidars are used to detect obstacles and distance information around the vehicle. The on-board environmental perception module is used to detect surrounding light, noise, air quality and other indicators.

[0072] Step 202: when acquiring the original data set, record the amount of original data in the original data set.

[0073] For example, when acquiring the original data set, the number of original data in the original data set is recorded to facilitate determining the data in the original data set that is in a preset state.

[0074] Step 203: When the amount of the original data is less than a preset threshold, the original data is used as the first data and added to the first data set.

[0075] For example, when the amount of original data is less than a preset threshold, it indicates that the original data is data in a preset state, and the original data is taken as the first data and added to the first data set.

[0076] Step 204: perform a data enhancement operation on the first data in the first data set to obtain enhanced data corresponding to the first data; the first data set includes data obtained under a preset state.

[0077] This step may specifically refer to the above step 102, which will not be described in detail here.

[0078] The preset states include: the vehicle is in a sharp turn state, the vehicle is in an emergency braking state, and the vehicle is in an acceleration state.

[0079] Optionally, step 204 may specifically include:

[0080] Sub-step 2041, dividing the first data set into an image set, a voice set and a time series set according to the presentation form of the data; the time series set includes data collected along with timestamps.

[0081] Sub-step 2042, performing image enhancement operations on the images in the image set respectively, obtaining an enhanced image corresponding to each of the images, and using the enhanced image as enhancement data corresponding to the image; the image enhancement operations include: one or more of image rotation, image translation, and image cropping;

[0082] Sub-step 2043, performing speech enhancement operations on the speech in the speech set respectively, obtaining enhanced speech corresponding to each of the speech, and using the enhanced speech as enhanced data corresponding to the speech; the speech enhancement operation includes: one or more of speech stretching, speech compression, and speech fusion;

[0083] Sub-step 2044, performing time series perturbation operations on the time series data in the time series set respectively, obtaining enhanced time series data corresponding to each of the time series data, and using the enhanced time series data as enhanced data corresponding to the time series data; the time series perturbation operation includes: one or more of random jitter and dynamic difference.

[0084] For sub-steps 2041 to 2044, image rotation is the most commonly used data enhancement method in the field of image processing, which includes various rotation methods such as random angle rotation and multi-angle rotation; image translation is another common image data enhancement method, which is similar to rotation and also includes random translation, proportional translation and multi-directional translation; image cropping includes multi-scale cropping and combined cropping, which can generate richer local information and improve data diversity compared to the above two methods.

[0085] For example, take the image of a cat as an example, see Figure 4 , Figure 4 The original image of the cat is shown. By rotating the cat, you can get the rotated image. Figure 5 , Figure 5 The image shown here is the image of the cat after it has been rotated. Of course, you can also translate and crop the cat.

[0086] For example, speech stretching is to change the time structure of speech by stretching the time dimension of speech data, so as to change the speaking speed; speech compression is to change the time structure of speech by compressing the time dimension of speech data, so as to change the speaking speed; speech fusion is to superimpose the speech data of two or more speakers to generate new speech data, all of which play the role of enhancing data.

[0087] For example, random jittering of time series data can simulate the different reaction times and operation modes of drivers in emergency situations; dynamic interpolation uses an interpolation algorithm to generate new intermediate data points between the original time series data, increasing the smoothness and continuity of the data to simulate a more realistic driving process.

[0088] Step 205: Add the enhanced data and the original data in the original data set to the merged data set, perform a preprocessing operation on the data in the merged data set, and obtain the preprocessed data of the data in the merged data set.

[0089] This step may be specifically referred to as the above step 103, which will not be described in detail here.

[0090] Optionally, the data in the combined data set includes: driver data, voice data and vehicle data. Step 205 may specifically include:

[0091] Sub-step 2051, denoising the driver data by a median filtering method to obtain denoised driver data;

[0092] Sub-step 2052, reducing the dimension of the denoised driver data by a principal component analysis method to obtain driver data after dimension reduction, and using the driver data after dimension reduction as preprocessed data of the driver data;

[0093] Sub-step 2053, using speech recognition technology to convert the speech data into text information, and using the text information as pre-processed data of the speech data;

[0094] Sub-step 2054, extracting features from the vehicle data, and normalizing the extracted features to obtain normalized vehicle data, and using the normalized vehicle data as preprocessed data of the vehicle data; the normalized vehicle data is used to characterize that the vehicle data is at the same dimensional level.

[0095] For sub-steps 2051-2054, see Figure 6 , Figure 6The data preprocessing in includes: driver data preprocessing, voice data preprocessing and vehicle data preprocessing. For driver data, most physiological signals can be denoised by median filtering. Median filtering divides the physiological signal image into several small filter windows. For each filter window, all pixel values ​​or sampling values ​​are sorted by size, and then the middle value is taken as the output value of the window. The median outputs of all filter windows are combined to form the final filter result image or signal. Then, physiological indicator features such as heart rate and heart rate variability can be extracted. For high-dimensional physiological signals, principal component analysis can be used for dimensionality reduction. Principal component analysis can map high-dimensional data to low-dimensional space, retain the most important information in the data, and effectively remove noise.

[0096] For example, see Figure 7 For voice data, speech recognition technology using deep learning models can convert voice data into text information. The neural network-based model can automatically learn the complex features in voice signals. Compared with traditional rule-based or statistical model-based methods, it significantly improves the accuracy of speech recognition. In addition, the deep learning model can directly input the original voice signal to the final text output, achieving end-to-end learning and prediction without the need for complex feature engineering, which greatly simplifies the design and development of voice recognition and improves the overall performance of the system.

[0097] For example, for vehicle data, features are extracted from the vehicle data, and operations such as standardization or normalization are performed to make each feature at the same order of magnitude; different types of vehicle data are integrated, and the collected heterogeneous data are converted and unified in format to ensure that the vehicle data have the same timestamp and spatial coordinates. For vehicle data with different time frequencies and spatial resolutions, spatiotemporal interpolation and alignment are required to ensure the spatiotemporal consistency of the vehicle data, which is conducive to subsequent data query and analysis; for data that need to be processed and analyzed quickly, such as weather changes and road conditions, real-time data streams are used, and stream processing technology is used for processing and analysis to achieve real-time monitoring and early warning. Based on the data collected by various on-board sensors, the deep learning model can accurately predict the vehicle's energy consumption and provide a basis for energy optimization. At the same time, time series analysis of on-board data that changes over time can also make full use of the advantages of deep learning. Time series models such as Transformer and TS-GAN can deeply explore the complex patterns and inherent laws in the data, thereby greatly improving the performance of tasks such as time series prediction, anomaly detection, and classification, and preparing pre-data processing for subsequent tasks such as vehicle trajectory prediction. This on-board data analysis and processing based on deep learning will surely play an increasingly important role in the future.

[0098] Step 206: Distributed storage of the preprocessed data according to the characteristics of the preprocessed data.

[0099] This step may be specifically referred to as the above step 104, which will not be described in detail here.

[0100] Optionally, the pre-processed data is divided into time series data, semi-structured data, and time-sensitive data. Step 206 may specifically include:

[0101] Sub-step 2061, storing the time series data and timestamp associated with time in a time series database;

[0102] Sub-step 2062, storing the semi-structured data having complex data types in a document-based database;

[0103] Sub-step 2063, storing the time-effectiveness data and index whose response speed exceeds a preset value in the memory database.

[0104] For sub-steps 2061 and 2062, a database specifically for time series data is used for time series data. The time series database can process and analyze data in real time, and can efficiently store and manage time series data. In addition, the time series database usually supports multi-dimensional analysis, and can slice and analyze time series data in various dimensions, such as by time, geographic location, device type, etc., providing a pre-processing solution for subsequent data processing.

[0105] For example, using a document-based database, you can store semi-structured data, such as voice data of drivers and passengers. The document type has a flexible data model and is suitable for storing complex data types. Document databases usually have built-in full-text search functions, which can quickly perform full-text search and retrieval on stored documents. It is very suitable for voice-to-text or text query and analysis, and document databases usually have good horizontal scalability and can dynamically add more storage nodes according to the growth of data volume to meet the storage needs of large-scale voice and text data.

[0106] For example, an in-memory database can be used to store data with high real-time requirements, such as vehicle speed and vehicle trajectory. Since the data is stored in memory, it is very suitable for fast query and analysis of real-time road conditions and surrounding information. At the same time, the in-memory database has good concurrency performance and can support concurrent access by a large number of clients, making it suitable for processing a large amount of real-time road conditions and surrounding information data.

[0107] Optionally, the method further includes:

[0108] Step B1, encrypting the preprocessed data by an encryption algorithm to obtain encrypted data; the encryption algorithm includes: a symmetric encryption algorithm, an asymmetric encryption algorithm, a message digest algorithm, and a digital signature algorithm;

[0109] Step 206 may further include:

[0110] Sub-step 2064, performing distributed storage on the encrypted data according to the characteristics of the pre-processed data.

[0111] Regarding step B1, data encryption is to process the original plain text file or data according to a certain algorithm to make it an unreadable code, usually called ciphertext, in order to achieve the purpose of protecting data. Encryption algorithms can be roughly divided into four categories: symmetric encryption algorithms, asymmetric encryption algorithms, message digest algorithms, and digital signature algorithms.

[0112] See also Figure 8 , Figure 8 Two encryption algorithms, symmetric encryption and asymmetric encryption, are demonstrated. In symmetric encryption, the encryption and decryption processes use the same key, encrypting the preprocessed data into ciphertext through the key, and then decrypting the ciphertext into the preprocessed data through the same key. In asymmetric encryption, the encryption and decryption processes use different keys, encrypting the preprocessed data into ciphertext through the public key, and then decrypting the ciphertext into the preprocessed data through the private key.

[0113] For example, the main feature of the message digest algorithm is that the encryption process does not require a key, and the encrypted data cannot be decrypted. The only algorithm that can be decrypted and reversed is the CRC32 algorithm. Only by inputting the same plaintext data and passing it through the same message digest algorithm can the same ciphertext be obtained.

[0114] Digital signature is a technology that implements the functions of stamping and signing in the computer world. Digital signature can identify tampering and disguise, and prevent denial. Due to its unforgeable, verifiable, and digital characteristics, it is used in the field of data encryption and data security and reliability.

[0115] For example, when storing preprocessed data, a hash function is used to generate a summary from the preprocessed data, and then the summary is encrypted with a private key. The encrypted summary will be stored together with the preprocessed data as a digital signature of the preprocessed data. When the data needs to be obtained, the user uses the same hash function to calculate the summary from the preprocessed data, and then uses the public key to decrypt the digital signature. If the two summaries are the same, then it can be confirmed that the ciphertext corresponding to the preprocessed data is the ciphertext generated using the private key.

[0116] See also Fig. 9 The signature algorithm generates a ciphertext and a signature 32E42A corresponding to the preprocessed data according to the preprocessed data and the private key; and verifies whether the ciphertext corresponding to the preprocessed data is the ciphertext generated using the private key according to the signature 32E42A and the public key corresponding to the preprocessed data.

[0117] For example, for sub-step 2064, after obtaining the encrypted data, the encrypted data is distributedly stored according to the characteristics of the pre-processed data. Through encrypted storage, data can be prevented from being obtained or leaked by unauthorized personnel, thereby protecting the company's business secrets and customer privacy. Encrypted storage can also prevent data from being tampered with or destroyed, ensuring the accuracy and credibility of the data.

[0118] Optionally, the method further includes:

[0119] Step 207, calculating the access frequency of the preprocessed data.

[0120] Step 208, when the access frequency of the preprocessed data is greater than or equal to a preset frequency, storing the preprocessed data locally;

[0121] Step 209 , when the access frequency of the preprocessed data is less than a preset frequency, the preprocessed data is stored in the cloud.

[0122] For sub-steps 207 to 209, taking the preset frequency of 60% as an example, when the access frequency of the pre-processed data is greater than or equal to 60%, the pre-processed data is stored locally, and when the access frequency of the pre-processed data is less than 60%, the pre-processed data is stored in the cloud. Based on the access frequency of the data, the data storage method is dynamically adjusted to optimize the storage cost and access speed.

[0123] For example, for applications that have high requirements for data security and control, you can consider establishing a local data center.

[0124] For example, different cloud service providers such as AWS, Azure, Google Cloud, etc. are used based on factors such as cost, geographical location, and service availability.

[0125] For example, thanks to the cloud platform's massive storage capacity, powerful computing power, and security and reliability, the cloud platform has naturally become an excellent solution for massive data analysis. The cloud platform provides almost unlimited data storage space and can carry massive data sets. Users can easily manage and access these large-scale data resources; the cloud platform has powerful distributed computing capabilities and can quickly process large-scale data; the cloud platform supports multi-user collaboration, and team members can easily share and access data resources; the cloud platform provides powerful data security and backup mechanisms to protect data from loss, and also provides access control and other functions to ensure data security and privacy.

[0126] In an embodiment of the present invention, by collecting data from the autonomous driving domain and data from the cockpit domain, and adding the data from the autonomous driving domain and data from the cockpit domain to the original data set, obtaining a first data set in the original data set, performing a data enhancement operation on the first data in the first data set, obtaining enhanced data corresponding to the first data, adding the enhanced data and the original data in the original data set to the merged data set, performing a preprocessing operation on the data in the merged data set, and obtaining preprocessed data of the data in the merged data set, not only the data from the autonomous driving domain but also the data from the cockpit domain are collected, and data enhancement is performed on the first data in the autonomous driving domain and the cockpit domain, so that the types of data obtained are more numerous and more comprehensive. In addition, according to the characteristics of the preprocessed data, the preprocessed data is distributedly stored, and the preprocessed data is stored in an appropriate location, so that the data can be obtained according to the storage location of the preprocessed data, rather than from the domain to which the data belongs. Therefore, when a user queries data, the complexity of the user query can be reduced, thereby improving the user experience.

[0127] Fig.10 A data storage system provided by an embodiment of the present invention is referred to Fig.10,This system is mainly divided into five modules: data acquisition module: used to collect data from drivers, voice data and vehicle data; data enhancement module: used to divide the collected data into image data, voice data and time series data, and perform data enhancement to obtain enhanced data; data processing and encryption module: responsible for data compression, data encryption and data preprocessing of enhanced data to obtain preprocessed data, and during the preprocessing operation, real-time monitoring of the preprocessing process and feedback, after obtaining the preprocessed data, data analysis is performed on it; data storage module: using distributed storage, the preprocessed data is stored in the time series database, document database and memory database, which can ensure the reliability, high performance and cost-effectiveness of the vehicle-mounted big data, and establish a complete data index and query mechanism to provide a good data foundation for subsequent data analysis, processing and application; visualization interaction module: through the user input in the user interaction module, the embedding module converts the user input into a vector representation, and the data interaction module obtains the query results based on the vector representation, providing a user-friendly interface, intuitively displaying various driving data and analysis results, supporting multi-dimensional data exploration and visualization, and facilitating the analysis and understanding of drivers and managers.

[0128] Fig.11 is a user interaction schematic diagram provided by an embodiment of the present invention, referring to Fig.11 Users can submit their needs as input to the user interaction interface. During the user input process, the legality of the input can be verified in real time, that is, whether the query permission is available, and the corresponding results can be given. After the user submits the need, the interface will provide an entry for querying the processing progress of the need and view the current status of the query. At the same time, due to the integration of the embedded large language model (LLM), it has memory and context perception capabilities, and can use the previous query content and background information to better understand and answer the current question or request, identify the relevance of the question to the previous text, and combine the previous communication content to make a more comprehensive and appropriate response.

[0129] The embedding module is a very critical part of the system. It is located between the user interaction module and the data interaction module and plays a connecting role. Its main function is to convert the natural language input by the user into a digital vector representation that the model can understand and process, and integrate contextual information to generate a vector representation with richer semantics, enhance the ability to understand user input, and finally pass the processed embedding vector to the backend data interaction module for it to understand and call related functions. This process is very important for meeting the user's interaction needs. For the data interaction module, the embedding module converts natural language inputs in different formats into a unified digital vector representation, which provides a standardized input format for the data interaction module and simplifies the input processing logic.

[0130] The main function of the data interaction module is data query. It receives query requests from the embedded module, retrieves the required information from the corresponding data source and performs data fusion operations according to the call of the embedded module response, integrates and fuses the information retrieved from different data sources, and ensures the integrity and consistency of the query results. Finally, the integrated query results are returned to the embedded module for subsequent understanding and generation of feedback to the user interaction interface.

[0131] Fig.12 is a block diagram of a vehicle data storage device provided by an embodiment of the present invention, such as Fig.12 As shown, the device 30 comprises:

[0132] The acquisition module 301 is used to acquire data of the autonomous driving domain and the cockpit domain, and add the data of the autonomous driving domain and the cockpit domain to the original data set; the autonomous driving domain is a domain related to assisted driving; the cockpit domain is a domain related to internal interaction of the vehicle;

[0133] A data enhancement module 302 is used to obtain a first data set in the original data set, perform a data enhancement operation on the first data in the first data set, and obtain enhanced data corresponding to the first data; the first data set includes data obtained in a preset state;

[0134] A preprocessing module 303 is used to add the enhanced data and the original data in the original data set to the merged data set, perform a preprocessing operation on the data in the merged data set, and obtain the preprocessed data of the data in the merged data set;

[0135] The storage module 304 is used to perform distributed storage on the preprocessed data according to the characteristics of the preprocessed data.

[0136] Optionally, the data enhancement module includes:

[0137] A division submodule, used to divide the first data set into an image set, a voice set and a time series set according to the presentation form of the data; the time series set includes data collected along with the timestamp;

[0138] An image enhancement submodule is used to perform image enhancement operations on the images in the image set respectively, obtain an enhanced image corresponding to each of the images, and use the enhanced image as enhancement data corresponding to the image; the image enhancement operation includes: one or more of image rotation, image translation, and image cropping;

[0139] A speech enhancement submodule is used to perform speech enhancement operations on the speech in the speech set respectively, obtain enhanced speech corresponding to each of the speech, and use the enhanced speech as enhanced data corresponding to the speech; the speech enhancement operation includes: one or more of speech stretching, speech compression, and speech fusion;

[0140] The time series enhancement submodule is used to perform time series perturbation operations on the time series data in the time series set respectively, obtain enhanced time series data corresponding to each of the time series data, and use the enhanced time series data as the enhanced data corresponding to the time series data; the time series perturbation operation includes: one or more of random jitter and dynamic difference.

[0141] Optionally, the data in the combined data set includes: driver data, voice data and vehicle data;

[0142] The preprocessing module comprises:

[0143] A denoising submodule, used for denoising the driver data by a median filtering method to obtain denoised driver data;

[0144] A dimensionality reduction submodule, used for reducing the dimensionality of the denoised driver data by a principal component analysis method to obtain driver data after dimensionality reduction, and using the driver data after dimensionality reduction as preprocessed data of the driver data;

[0145] A voice conversion submodule, used to convert the voice data into text information by using voice recognition technology, and use the text information as pre-processed data of the voice data;

[0146] The normalization submodule is used to extract features from the vehicle data and normalize the extracted features to obtain normalized vehicle data, and use the normalized vehicle data as preprocessed data of the vehicle data; the normalized vehicle data is used to characterize that the vehicle data is at the same dimensional level.

[0147] Optionally, the preprocessed data is divided into time series data, semi-structured data, and time-sensitive data;

[0148] The storage module comprises:

[0149] A first storage submodule, used for storing the time series data and timestamp related to time in a time series database;

[0150] A second storage submodule, used for storing the semi-structured data with complex data types in a document-type database;

[0151] The third storage submodule is used to store the time-sensitivity data and index whose response speed exceeds a preset value in a memory database.

[0152] Optionally, the acquisition module includes:

[0153] A recording submodule, used for recording the amount of original data in the original data set when acquiring the original data set;

[0154] The adding submodule is used to add the original data as the first data to the first data set when the amount of the original data is less than a preset threshold.

[0155] Optionally, the device further comprises:

[0156] An encryption module, used to encrypt the preprocessed data by an encryption algorithm to obtain encrypted data; the encryption algorithm includes: a symmetric encryption algorithm, an asymmetric encryption algorithm, a message digest algorithm, and a digital signature algorithm;

[0157] The storage module comprises:

[0158] The fourth storage submodule is used to perform distributed storage on the encrypted data according to the characteristics of the preprocessed data.

[0159] Optionally, the device further comprises:

[0160] A calculation module, used for calculating the access frequency of the preprocessed data;

[0161] A local storage module, used for storing the preprocessed data locally when the access frequency of the preprocessed data is greater than or equal to a preset frequency;

[0162] The cloud storage module is used to store the preprocessed data in the cloud when the access frequency of the preprocessed data is less than a preset frequency.

[0163] Optionally, the data in the autonomous driving domain includes: vehicle data; the data in the cockpit domain includes: driver data and voice data;

[0164] The driver data includes: driver's physiological data, driver's facial data, and driver's driving operation data;

[0165] The voice data includes: voice data between the driver and the vehicle system, and voice data between the driver and the passenger;

[0166] The vehicle data includes: the working status of vehicle components, the vehicle's driving speed, the vehicle's geographic coordinates, the vehicle's driving trajectory, the vehicle's temperature, the vehicle's air quality, and the distance between the vehicle and surrounding obstacles.

[0167] In summary, in the embodiment of the present invention, by collecting data in the autonomous driving domain and data in the cockpit domain, and adding the data in the autonomous driving domain and data in the cockpit domain to the original data set, obtaining the first data set in the original data set, performing data enhancement operation on the first data in the first data set, obtaining enhanced data corresponding to the first data, adding the enhanced data and the original data in the original data set to the merged data set, performing preprocessing operation on the data in the merged data set, and obtaining preprocessed data of the data in the merged data set, not only the data in the autonomous driving domain but also the data in the cockpit domain are collected, and data enhancement is performed on the first data in the autonomous driving domain and the cockpit domain, so that the types of data obtained are more and more comprehensive. In addition, according to the characteristics of the preprocessed data, the preprocessed data is distributedly stored, and the preprocessed data is stored in an appropriate location. The data can be obtained according to the storage location of the preprocessed data, rather than from the domain to which the data belongs. Therefore, when the user queries the data, the complexity of the user query can be reduced, and the user experience is improved.

[0168] Fig.13 4 is a block diagram of an electronic device 400 provided by an embodiment of the present invention. For example, the electronic device 400 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0169] Reference Fig.13 , the electronic device 400 may include one or more of the following components: a processing component 402 , a memory 404 , a power component 406 , a multimedia component 408 , an audio component 410 , an input / output (I / O) interface 412 , a sensor component 414 , and a communication component 416 .

[0170] The processing component 402 generally controls the overall operation of the electronic device 400, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 402 may include one or more modules to facilitate the interaction between the processing component 402 and other components. For example, the processing component 402 may include a multimedia module to facilitate the interaction between the multimedia component 408 and the processing component 402.

[0171] The memory 404 is used to store various types of data to support the operation of the electronic device 400. Examples of such data include instructions for any application or method operating on the electronic device 400, contact data, phone book data, messages, pictures, multimedia, etc. The memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0172] The power supply component 406 provides power to the various components of the electronic device 400. The power supply component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 400.

[0173] The multimedia component 408 includes a screen that provides an output interface between the electronic device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front camera and / or a rear camera. When the electronic device 400 is in an operating mode, such as a shooting mode or a multimedia mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0174] The audio component 410 is used to output and / or input audio signals. For example, the audio component 410 includes a microphone (MIC), and when the electronic device 400 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is used to receive an external audio signal. The received audio signal can be further stored in the memory 404 or sent via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting audio signals.

[0175] I / O interface 412 provides an interface between processing component 402 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0176] The sensor assembly 414 includes one or more sensors for providing various aspects of status assessment for the electronic device 400. For example, the sensor assembly 414 can detect the open / closed state of the electronic device 400, the relative positioning of components, such as the display and keypad of the electronic device 400, and the sensor assembly 414 can also detect the position change of the electronic device 400 or a component of the electronic device 400, the presence or absence of user contact with the electronic device 400, the orientation or acceleration / deceleration of the electronic device 400, and the temperature change of the electronic device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 414 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0177] The communication component 416 is used to facilitate wired or wireless communication between the electronic device 400 and other devices. The electronic device 400 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0178] In an exemplary embodiment, the electronic device 400 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to implement a vehicle data storage method provided in an embodiment of the present invention.

[0179] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, and the instructions can be executed by a processor 420 of an electronic device 400 to perform the above method. For example, the non-transitory storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0180] Fig.14is a block diagram of another electronic device 500 provided in an embodiment of the present invention. For example, the electronic device 500 may be provided as a server. Figure 5 The electronic device 500 includes a processing component 522, which further includes one or more processors, and a memory resource represented by a memory 532 for storing instructions executable by the processing component 522, such as an application. The application stored in the memory 532 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 522 is configured to execute instructions to perform a vehicle data storage method provided by an embodiment of the present invention.

[0181] The electronic device 500 may also include a power supply component 526 configured to perform power management of the electronic device 500, a wired or wireless network interface 550 configured to connect the electronic device 500 to a network, and an input / output (I / O) interface 558. The electronic device 500 may operate based on an operating system stored in the memory 532.

[0182] An embodiment of the present invention further provides a computer program product, including a computer program, and a vehicle data storage method implemented when the computer program is executed by a processor.

[0183] Those skilled in the art will readily appreciate other embodiments of the invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0184] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A vehicle data storage method, characterized in that: include: Collecting data from the autonomous driving domain and data from the cockpit domain, and adding the data from the autonomous driving domain and the data from the cockpit domain to an original data set; The autonomous driving domain is a domain related to assisted driving; the cockpit domain is a domain related to vehicle internal interaction; Acquire a first data set in the original data set, perform a data enhancement operation on first data in the first data set, and obtain enhanced data corresponding to the first data; the first data set includes data obtained in a preset state; Adding the enhanced data and the original data in the original data set to the merged data set, performing a preprocessing operation on the data in the merged data set, and obtaining preprocessed data of the data in the merged data set; The preprocessed data is distributedly stored according to the characteristics of the preprocessed data.

2. The method according to claim 1, characterized in that: The performing a data enhancement operation on the first data in the first data set to obtain enhanced data corresponding to the first data includes: According to the presentation form of the data, the first data set is divided into an image set, a voice set and a time series set; the time series set includes data collected with a timestamp; Performing image enhancement operations on the images in the image set respectively to obtain enhanced images corresponding to each of the images, and using the enhanced images as enhanced data corresponding to the images; the image enhancement operations include: one or more of image rotation, image translation, and image cropping; Performing speech enhancement operations on the speech in the speech set respectively to obtain enhanced speech corresponding to each of the speech, and using the enhanced speech as enhanced data corresponding to the speech; the speech enhancement operation includes: one or more of speech stretching, speech compression, and speech fusion; Perform time series perturbation operations on the time series data in the time series set respectively to obtain enhanced time series data corresponding to each of the time series data, and use the enhanced time series data as enhanced data corresponding to the time series data; the time series perturbation operation includes: one or more of random jitter and dynamic difference.

3. The method according to claim 1, characterized in that The data in the combined data set includes: driver data, voice data and vehicle data; The preprocessing operation is performed on the data in the merged data set to obtain the preprocessed data in the merged data set, including: De-noising the driver data by using a median filtering method to obtain de-noised driver data; Performing dimensionality reduction on the denoised driver data by a principal component analysis method to obtain dimensionality reduced driver data, and using the dimensionality reduced driver data as preprocessed data of the driver data; Using speech recognition technology to convert the speech data into text information, and using the text information as pre-processed data of the speech data; Feature extraction is performed on the vehicle data, and the extracted features are normalized to obtain normalized vehicle data, and the normalized vehicle data is used as preprocessed data of the vehicle data; the normalized vehicle data is used to characterize that the vehicle data are at the same dimensional level.

4. The method according to any one of claims 1 to 3, characterized in that: The pre-processed data is divided into time series data, semi-structured data, and time-sensitive data; The distributed storage of the preprocessed data according to the characteristics of the preprocessed data includes: Storing the time series data and timestamps related to time in a time series database; Storing the semi-structured data having complex data types in a document-type database; The time-sensitive data and indexes whose response speed exceeds a preset value are stored in a memory database.

5. The method according to claim 1, characterized in that The obtaining of the first data set in the original data set comprises: When acquiring the original data set, recording the amount of original data in the original data set; When the amount of the original data is less than a preset threshold, the original data is taken as first data and added to the first data set.

6. The method according to claim 1-3 or 5, characterized in that: The method further comprises: Encrypting the preprocessed data by an encryption algorithm to obtain encrypted data; the encryption algorithm includes: a symmetric encryption algorithm, an asymmetric encryption algorithm, a message digest algorithm, and a digital signature algorithm; The distributed storage of the preprocessed data according to the characteristics of the preprocessed data includes: The encrypted data is distributedly stored according to the characteristics of the preprocessed data.

7. The method according to any one of claims 1 to 3, 5 or 6, characterized in that: The method further comprises: Calculate the access frequency of the preprocessed data; When the access frequency of the preprocessed data is greater than or equal to a preset frequency, storing the preprocessed data locally; When the access frequency of the preprocessed data is less than a preset frequency, the preprocessed data is stored in the cloud.

8. The method according to claim 1, characterized in that: The data in the autonomous driving domain includes: vehicle data; the data in the cockpit domain includes: driver data and voice data; The driver data includes: driver's physiological data, driver's facial data, and driver's driving operation data; The voice data includes: voice data between the driver and the vehicle system, and voice data between the driver and the passenger; The vehicle data includes: the working status of vehicle components, the vehicle's driving speed, the vehicle's geographic coordinates, the vehicle's driving trajectory, the vehicle's temperature, the vehicle's air quality, and the distance between the vehicle and surrounding obstacles.

9. A vehicle data storage device, characterized in that: include: a collection module, used to collect data from an autonomous driving domain and data from a cockpit domain, and add the data collected from the autonomous driving domain and the cockpit domain to an original data set; the autonomous driving domain is a domain related to assisted driving; the cockpit domain is a domain related to internal vehicle interaction; A data enhancement module, used to obtain a first data set in the original data set, perform a data enhancement operation on the first data in the first data set, and obtain enhanced data corresponding to the first data; the first data set includes data obtained in a preset state; A preprocessing module, used for adding the enhanced data and the original data in the original data set to the merged data set, performing a preprocessing operation on the data in the merged data set, and obtaining the preprocessed data of the data in the merged data set; The storage module is used to perform distributed storage on the preprocessed data according to the characteristics of the preprocessed data.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by a processor, the steps of the vehicle data storage method according to any one of claims 1 to 8 are implemented.

Images